DocumentCode
1714450
Title
Fuzzy looper control with neural-net based tuning for rolling mills
Author
Janabi-Sharifi, F. ; Fan, J.
Author_Institution
Dept. of Mech., Aerosp., & Ind. Eng., Ryerson Univ., Toronto, Ont., Canada
Volume
2
fYear
2001
Firstpage
626
Abstract
Traditional looper control methods cannot deal effectively with unmodeled dynamics and large variations which can lead to scrap runs and damages to machinery in steel industry. This paper presents the design of a fuzzy looper control with neural-net based tuning of rule-base and defuzzification. The effects of various design options are discussed and practical conclusions are made. Also, the results are compared with the results of different initial rule-bases, PID control, and with membership function tuning.
Keywords
closed loop systems; fuzzy control; inference mechanisms; neural nets; neurocontrollers; rolling mills; steel industry; three-term control; tuning; PID control; defuzzification; fuzzy control; fuzzy inference; loop control; membership function tuning; neural-net; rolling mills; rule-base; steel industry; tuning; unmodeled dynamics; Automatic control; Control systems; Error correction; Fuzzy control; Laboratories; Manufacturing automation; Milling machines; Robust control; Three-term control; Tuning;
fLanguage
English
Publisher
ieee
Conference_Titel
Fuzzy Systems, 2001. The 10th IEEE International Conference on
Print_ISBN
0-7803-7293-X
Type
conf
DOI
10.1109/FUZZ.2001.1009032
Filename
1009032
Link To Document